init test

Browse files

Files changed (8) hide show

README.md +1 -1
config.json +1 -1
replay.mp4 +2 -2
results.json +1 -1
thicc-ppo-LunarLander-rc.zip +2 -2
thicc-ppo-LunarLander-rc/data +32 -30
thicc-ppo-LunarLander-rc/policy.optimizer.pth +2 -2
thicc-ppo-LunarLander-rc/policy.pth +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -161.45 +/- 133.23
       name: mean_reward
     task:
       type: reinforcement-learning

   results:
   - metrics:
     - type: mean_reward
+      value: -1224.44 +/- 946.78
       name: mean_reward
     task:
       type: reinforcement-learning

config.json CHANGED Viewed

@@ -1 +1 @@

- {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f40208d8ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f40208d8f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f40208dc040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f40208dc0d0>", "_build": "<function ActorCriticPolicy._build at 0x7f40208dc160>", "forward": "<function ActorCriticPolicy.forward at 0x7f40208dc1f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f40208dc280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f40208dc310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f40208dc3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f40208dc430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f40208dc4c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f40208da1b0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWV4wAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlChLgEtAfZQojAJwaZRdlEsgYYwCdmaUXZRLIGF1ZYwPb3B0aW1pemVyX2NsYXNzlIwTdG9yY2gub3B0aW0ucm1zcHJvcJSMB1JNU3Byb3CUk5SMEG9wdGltaXplcl9rd2FyZ3OUfZQojAVhbHBoYZRHP++uFHrhR66MA2Vwc5RHPuT4tYjjaPGMDHdlaWdodF9kZWNheZRLAHV1Lg==", "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>", "net_arch": [128, 64, {"pi": [32], "vf": [32]}], "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 256, "num_timesteps": 5242880, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651717282.5445883, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5, "n_steps": 4096, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.4.0-109-lowlatency-x86_64-with-glibc2.29 #123-Ubuntu SMP PREEMPT Fri Apr 8 09:52:18 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

+ {"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n Policy class for actor-critic algorithms (has both policy and value prediction).\n Used by A2C, PPO and the likes.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param ortho_init: Whether to use or not orthogonal initialization\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param full_std: Whether to use (n_features x n_actions) parameters\n for the std instead of only (n_features,) when using gSDE\n :param sde_net_arch: Network architecture for extracting features\n when using gSDE. If None, the latent features from the policy will be used.\n Pass an empty list to use the states as features.\n :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param squash_output: Whether to squash the output using a tanh function,\n this allows to ensure boundaries when using gSDE.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7724632ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7724632f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7724636040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77246360d0>", "_build": "<function ActorCriticPolicy._build at 0x7f7724636160>", "forward": "<function ActorCriticPolicy.forward at 0x7f77246361f0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7724636280>", "_predict": "<function ActorCriticPolicy._predict at 0x7f7724636310>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77246363a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7724636430>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77246364c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f77246331b0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVZwAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlChLgEtAfZQojAJwaZRdlEsgYYwCdmaUXZRLIGF1ZXUu", "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>", "net_arch": [128, 64, {"pi": [32], "vf": [32]}]}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False]", "bounded_above": "[False False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 256, "num_timesteps": 1048576, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1651723276.0331068, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.04857599999999995, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 4, "n_steps": 4096, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 256, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.4.0-109-lowlatency-x86_64-with-glibc2.29 #123-Ubuntu SMP PREEMPT Fri Apr 8 09:52:18 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

replay.mp4 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f0883757cd5d8c21b09c47818a84a10d81e6f1548ccf2ba5306ad44a051789
-size 211967

 version https://git-lfs.github.com/spec/v1
+oid sha256:7b8d5843c93453d3d7d4fb6a9522de1d9e26d5b6dff65a367ec222c109163ceb
+size 162210

results.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"mean_reward": -~~161~~.~~45235933635448~~, "std_reward": ~~133~~.~~23168004046548~~, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-~~05T10~~:33:27.~~472783~~"}


1	+ {"mean_reward": -1224.438580530847, "std_reward": 946.7833483504636, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-05T12:04:58.915570"}

thicc-ppo-LunarLander-rc.zip CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ddcf7818f18d715a84201678e1591faae1bbcaa34c14955921408cbbe1001c3
-size 143534

 version https://git-lfs.github.com/spec/v1
+oid sha256:6354b847b907343698489945cce98f7eac4413508cb5b9945f8a40853ec06f84
+size 202407

thicc-ppo-LunarLander-rc/data CHANGED Viewed

@@ -4,24 +4,24 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f40208d8ee0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f40208d8f70>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f40208dc040>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f40208dc0d0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f40208dc160>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f40208dc1f0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f40208dc280>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f40208dc310>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f40208dc3a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f40208dc430>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f40208dc4c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f40208da1b0>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
-        ":serialized:": "gAWV4wAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlChLgEtAfZQojAJwaZRdlEsgYYwCdmaUXZRLIGF1ZYwPb3B0aW1pemVyX2NsYXNzlIwTdG9yY2gub3B0aW0ucm1zcHJvcJSMB1JNU3Byb3CUk5SMEG9wdGltaXplcl9rd2FyZ3OUfZQojAVhbHBoYZRHP++uFHrhR66MA2Vwc5RHPuT4tYjjaPGMDHdlaWdodF9kZWNheZRLAHV1Lg==",
         "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
         "net_arch": [
             128,
@@ -34,13 +34,7 @@
                     32
                 ]
             }
-        ],
-        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
-        "optimizer_kwargs": {
-            "alpha": 0.99,
-            "eps": 1e-05,
-            "weight_decay": 0
-        }
     },
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
@@ -64,25 +58,25 @@
         "_np_random": null
     },
     "n_envs": 256,
-    "num_timesteps": 5242880,
-    "_total_timesteps": 5000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1651717282.5445883,
-    "learning_rate": 0.0007,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiTQABhZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
@@ -91,18 +85,26 @@
     "_current_progress_remaining": -0.04857599999999995,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 5,
     "n_steps": 4096,
     "gamma": 0.999,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "normalize_advantage": false
 }

         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f7724632ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f7724632f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f7724636040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f77246360d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f7724636160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f77246361f0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f7724636280>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f7724636310>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f77246363a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f7724636430>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f77246364c0>",
         "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7f77246331b0>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVZwAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARUYW5olJOUjAhuZXRfYXJjaJRdlChLgEtAfZQojAJwaZRdlEsgYYwCdmaUXZRLIGF1ZXUu",
         "activation_fn": "<class 'torch.nn.modules.activation.Tanh'>",
         "net_arch": [
             128,
                     32
                 ]
             }
+        ]
     },
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
         "_np_random": null
     },
     "n_envs": 256,
+    "num_timesteps": 1048576,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
+    "start_time": 1651723276.0331068,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
+        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "_current_progress_remaining": -0.04857599999999995,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVHxAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIk6mCUcmrY8CUhpRSlIwBbJRLTIwBdJRHQGH3enhsImh1fZQoaAZoCWgPQwj9L9eiBRhXwJSGlFKUaBVLW2gWR0Bh+ZMDfWMCdX2UKGgGaAloD0MI1GNbBpyzXsCUhpRSlGgVS2FoFkdAYfmM4LkS3HV9lChoBmgJaA9DCJwyN9+IkFrAlIaUUpRoFUtPaBZHQGH5ZeZ5Rj11fZQoaAZoCWgPQwgQPL69ayRUwJSGlFKUaBVLP2gWR0Bh+RuEVWS2dX2UKGgGaAloD0MIwOrIkQ7Ic8CUhpRSlGgVS2poFkdAYfkCsfaHsXV9lChoBmgJaA9DCIOG/gmu3G/AlIaUUpRoFUtnaBZHQGH6ASeyzHF1fZQoaAZoCWgPQwhnmrD9ZCRqwJSGlFKUaBVLfGgWR0Bh+fUc4o7WdX2UKGgGaAloD0MIVcGopA51cMCUhpRSlGgVS1poFkdAYfu+Y+jdpXV9lChoBmgJaA9DCC1CsRU0xF/AlIaUUpRoFUtUaBZHQGH8o3irDIl1fZQoaAZoCWgPQwi1wB4TKaxZwJSGlFKUaBVLcGgWR0Bh/KXv6TGHdX2UKGgGaAloD0MIu5wSEJOtdcCUhpRSlGgVS01oFkdAYf40BwMpgHV9lChoBmgJaA9DCCUk0jY+SXXAlIaUUpRoFUtmaBZHQGH+M5fdAPd1fZQoaAZoCWgPQwg34PPDCN1zwJSGlFKUaBVLc2gWR0Bh/fpbD/EPdX2UKGgGaAloD0MIZVBtcGLTdsCUhpRSlGgVS21oFkdAYf8jvd/KAHV9lChoBmgJaA9DCOfib3uC1VbAlIaUUpRoFUtWaBZHQGH/Gsmv4dp1fZQoaAZoCWgPQwgA5lq0gKJuwJSGlFKUaBVLUmgWR0Bh/qDf3vhIdX2UKGgGaAloD0MIHAx1WGEYb8CUhpRSlGgVS1NoFkdAYf6TnJT2nXV9lChoBmgJaA9DCAaE1sMXNmjAlIaUUpRoFUt4aBZHQGIAg6+36RB1fZQoaAZoCWgPQwhb07zjFEpYwJSGlFKUaBVLZWgWR0BiAING3F1kdX2UKGgGaAloD0MIIVwBhfrJYcCUhpRSlGgVS0ZoFkdAYgHS4vvjO3V9lChoBmgJaA9DCFt6NNWTgnPAlIaUUpRoFUthaBZHQGIBwcYIjW11fZQoaAZoCWgPQwhE3JxKRkxywJSGlFKUaBVLW2gWR0BiAWYhMajvdX2UKGgGaAloD0MIjUP9LmyPVcCUhpRSlGgVS1VoFkdAYgEe8PFvRHV9lChoBmgJaA9DCMwlVdtNAl3AlIaUUpRoFUtCaBZHQGIC1ymygPF1fZQoaAZoCWgPQwgRqP5BJH1lwJSGlFKUaBVLUGgWR0BiAthVlwtKdX2UKGgGaAloD0MIa4MT0a/gaMCUhpRSlGgVS19oFkdAYgPWBjFyaXV9lChoBmgJaA9DCOfG9IQlbkLAlIaUUpRoFUtcaBZHQGIGrX+VC5V1fZQoaAZoCWgPQwgbZ9MRQONgwJSGlFKUaBVLZGgWR0BiBpsKsuFpdX2UKGgGaAloD0MIrb8lAP8UPsCUhpRSlGgVS2VoFkdAYgYx8lXzUnV9lChoBmgJaA9DCMhAnl2+gVTAlIaUUpRoFUtIaBZHQGIGIkZ75VR1fZQoaAZoCWgPQwhslPWbiR1CwJSGlFKUaBVLZGgWR0BiBci0OVgQdX2UKGgGaAloD0MIDag3o+bJasCUhpRSlGgVS3VoFkdAYgi8WbgCOnV9lChoBmgJaA9DCCC4yhMIyVXAlIaUUpRoFUs6aBZHQGIIP6KtPpJ1fZQoaAZoCWgPQwjvb9BefephwJSGlFKUaBVLeGgWR0BiCgI2OyVwdX2UKGgGaAloD0MItDukGGDvdsCUhpRSlGgVS3VoFkdAYgtCWu5jIHV9lChoBmgJaA9DCKZgjbPprlfAlIaUUpRoFUtVaBZHQGILHtF8XvZ1fZQoaAZoCWgPQwg8FXDPc/x5wJSGlFKUaBVLb2gWR0BiCxzRx95RdX2UKGgGaAloD0MIkPgVa7jbYcCUhpRSlGgVS0toFkdAYgsl67dzn3V9lChoBmgJaA9DCKw41VoYB33AlIaUUpRoFUtUaBZHQGILAXMyJsR1fZQoaAZoCWgPQwgDzefc7X9uwJSGlFKUaBVLhGgWR0BiDNke6qbSdX2UKGgGaAloD0MIHsGNlC0FZsCUhpRSlGgVS1ZoFkdAYgyt7KJVKnV9lChoBmgJaA9DCG9kHvlD+3HAlIaUUpRoFUtxaBZHQGIMpB5X2dx1fZQoaAZoCWgPQwiaet0iMH5ZwJSGlFKUaBVLTWgWR0BiDIrSVnmJdX2UKGgGaAloD0MImboru2D2csCUhpRSlGgVS29oFkdAYgyHARChOHV9lChoBmgJaA9DCIi4OZUMa1TAlIaUUpRoFUs7aBZHQGINvlEJBxB1fZQoaAZoCWgPQwi0keumlH1SwJSGlFKUaBVLQ2gWR0BiDcNlRP43dX2UKGgGaAloD0MIvrwA++iZXcCUhpRSlGgVS1loFkdAYg8W1twaSHV9lChoBmgJaA9DCKd38X6cSHHAlIaUUpRoFUtfaBZHQGIOxCQcPvt1fZQoaAZoCWgPQwiPqFDdXLxWwJSGlFKUaBVLXmgWR0BiDqo60Y0mdX2UKGgGaAloD0MI8DMuHMh3ecCUhpRSlGgVS5RoFkdAYhB+OOsDGXV9lChoBmgJaA9DCMTOFDqvylnAlIaUUpRoFUtmaBZHQGIPcxCY1Hh1fZQoaAZoCWgPQwhJ2/gTFSJgwJSGlFKUaBVLS2gWR0BiEYkka/ATdX2UKGgGaAloD0MIkdCWc+n9eMCUhpRSlGgVS3JoFkdAYhGHRkVer3V9lChoBmgJaA9DCCjRksfTblvAlIaUUpRoFUtCaBZHQGIRHCfpUxV1fZQoaAZoCWgPQwjV6xaBsbNtwJSGlFKUaBVLe2gWR0BiER68g6ltdX2UKGgGaAloD0MIaRmp91QTbMCUhpRSlGgVS1RoFkdAYhEEEkjX4HV9lChoBmgJaA9DCDHrxVBOFkjAlIaUUpRoFUs/aBZHQGIQ6GHpKSR1fZQoaAZoCWgPQwh6yJQPQYtowJSGlFKUaBVLUWgWR0BiEilxffGddX2UKGgGaAloD0MIM05DVOFcbMCUhpRSlGgVS1BoFkdAYhISFoL5RHV9lChoBmgJaA9DCCgLX1/rB17AlIaUUpRoFUtMaBZHQGIUBTfixV11fZQoaAZoCWgPQwjKMsSxrt15wJSGlFKUaBVLcGgWR0BiE4CCBf8edX2UKGgGaAloD0MIr5gR3h5SZsCUhpRSlGgVS4hoFkdAYhVCBPKuCHV9lChoBmgJaA9DCKuUnukl/GLAlIaUUpRoFUtyaBZHQGIU9cB2fTV1fZQoaAZoCWgPQwiWP98WrC9iwJSGlFKUaBVLYmgWR0BiFFHnU2DQdX2UKGgGaAloD0MIog4r3PIXWMCUhpRSlGgVS09oFkdAYhYz/p+tsHV9lChoBmgJaA9DCDrrU45Jf2PAlIaUUpRoFUtcaBZHQGIVgoXsPat1fZQoaAZoCWgPQwhehZSfVB9AQJSGlFKUaBVN6ANoFkdAYhcg3cYZVHV9lChoBmgJaA9DCJur5jkivxLAlIaUUpRoFUtKaBZHQGIXJEx7AtZ1fZQoaAZoCWgPQwghPNo4Yr9cwJSGlFKUaBVLX2gWR0BiFxdOZb6hdX2UKGgGaAloD0MI8ZwtILRfYMCUhpRSlGgVS3toFkdAYhcJdB0IT3V9lChoBmgJaA9DCOGaO/rfFWXAlIaUUpRoFUtGaBZHQGIXAXuVopR1fZQoaAZoCWgPQwiWWu83Wi5gwJSGlFKUaBVLTWgWR0BiF932VVxTdX2UKGgGaAloD0MIHuBJC5fZW8CUhpRSlGgVS1loFkdAYhlKIznA7HV9lChoBmgJaA9DCKuy74pgUGPAlIaUUpRoFUt8aBZHQGIaqgAZKnN1fZQoaAZoCWgPQwgNN+DzQ5pvwJSGlFKUaBVLVGgWR0BiHHSQYDT0dX2UKGgGaAloD0MI5BBxcyrLbsCUhpRSlGgVS3toFkdAYhwUTL4etHV9lChoBmgJaA9DCKta0lEOoErAlIaUUpRoFUtAaBZHQGIdDrqt5lh1fZQoaAZoCWgPQwiXVkPingtiwJSGlFKUaBVLY2gWR0BiHQvUSZjQdX2UKGgGaAloD0MI9l580R6tZMCUhpRSlGgVS0loFkdAYh52K2rn1XV9lChoBmgJaA9DCL71Yb1RzFLAlIaUUpRoFUtIaBZHQGIgUkOZssR1fZQoaAZoCWgPQwgPZD21+mhYwJSGlFKUaBVLVWgWR0BiH4DRtxdZdX2UKGgGaAloD0MI6e3PRUPOV8CUhpRSlGgVSztoFkdAYiDNqQA+6nV9lChoBmgJaA9DCPlISnoYzXzAlIaUUpRoFUtbaBZHQGIiHk92X9l1fZQoaAZoCWgPQwind/F+XEFgwJSGlFKUaBVLT2gWR0BiIe/Ho5ggdX2UKGgGaAloD0MI88gfDLzVasCUhpRSlGgVS0RoFkdAYiHiQ1aW5nV9lChoBmgJaA9DCHDOiNLe21jAlIaUUpRoFUs9aBZHQGIj25H3Del1fZQoaAZoCWgPQwicbAN3oPpfwJSGlFKUaBVLa2gWR0BiI2lj3EhrdX2UKGgGaAloD0MICfoLPWIBbMCUhpRSlGgVS1NoFkdAYiVar3j+73V9lChoBmgJaA9DCG8O12oPDFXAlIaUUpRoFUtLaBZHQGIlIaDPGAF1fZQoaAZoCWgPQwibdcb3xQlDwJSGlFKUaBVLRWgWR0BiJNBQemvXdX2UKGgGaAloD0MIYK3aNSFoccCUhpRSlGgVS1FoFkdAYiSdnTRYzXV9lChoBmgJaA9DCEwXYvWH+HbAlIaUUpRoFUtyaBZHQGIkhxHXmNl1fZQoaAZoCWgPQwg83A4NS9d1wJSGlFKUaBVLVmgWR0BiJrzyz5XVdX2UKGgGaAloD0MIiPVGrfDcdsCUhpRSlGgVS1xoFkdAYiad4mkWRHV9lChoBmgJaA9DCAoQBTMm+nzAlIaUUpRoFUttaBZHQGIme2uxKQJ1fZQoaAZoCWgPQwgyIeaSqiZewJSGlFKUaBVLUmgWR0BiJnHPu5SWdX2UKGgGaAloD0MI4lzDDI17PECUhpRSlGgVTegDaBZHQGImU29+PR11fZQoaAZoCWgPQwgF/BpJguZgwJSGlFKUaBVLYGgWR0BiJji83++/dX2UKGgGaAloD0MIDixHyEDXWMCUhpRSlGgVS2VoFkdAYiYVWS2Yv3VlLg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
+    "_n_updates": 4,
     "n_steps": 4096,
     "gamma": 0.999,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
+    "batch_size": 256,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
 }

thicc-ppo-LunarLander-rc/policy.optimizer.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6314a9c091688a7ef82500b602bab56ffde14db6ca778f83b4f6d011c89c6268
-size 58305

 version https://git-lfs.github.com/spec/v1
+oid sha256:ee813b021d6ad46c7a371651318c75c0d5e6cf40ac757f27e8a6e78221ae13df
+size 116317

thicc-ppo-LunarLander-rc/policy.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f840fa41d2954bbad24e183c68a0e995f546758daa17812c8b39ade7e0b20abe
 size 58945

 version https://git-lfs.github.com/spec/v1
+oid sha256:d8021561f549c1e44a83e7d93a1a44c58b3b0ea8f0f5604c2851807dc68933e3
 size 58945